Performance-Oriented Neural Architecture Search
Authors:
- 1 July 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 177-184
Abstract
Hardware-Software Co-Design is a highly successful strategy for improving performance of domain-specific computing systems. We argue for the application of the same methodology to deep learning; specifically, we propose to extend neural architecture search with information about the hardware to ensure that the model designs produced are highly efficient in addition to the typical criteria around accuracy. Using the task of keyword spotting in audio on edge computing devices, we demonstrate that our approach results in neural architecture that is not only highly accurate, but also efficiently mapped to the computing platform which will perform the inference. Using our modified neural architecture search, we demonstrate 0.88% increase in TOP-I accuracy with $ 1.85\times$ reduction in latency for keyword spotting in audio on an embedded SoC, and $ 1.59\times$ on a high-end GPU.
Keywords
All Related Versions
This publication has 16 references indexed in Scilit:
- FINN- RACM Transactions on Reconfigurable Technology and Systems, 2018
- Weighted Quantization-Regularization in DNNs for Weight Memory Minimization Toward HW ImplementationIEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2018
- QUENN2018
- Optimal DNN primitive selection with partitioned boolean quadratic programming2018
- Parallel Multi Channel convolution using General Matrix Multiplication2017
- EIEACM SIGARCH Computer Architecture News, 2016
- Going deeper with convolutions2015
- Caffe2014
- Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research GroupsIEEE Signal Processing Magazine, 2012
- Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentencesIEEE Transactions on Acoustics, Speech, and Signal Processing, 1980